Commit graph

  • c9b78602d3
    refactor: modify DELETE API endpoints by returning HTTP 204 No Content + empty body instead of 200 OK + response body with null (#3112) IAN MILLER 2025-08-13 15:56:26 +01:00
  • 92aca434a7
    fix: Fix list_sessions() (#3114) Francisco Arceo 2025-08-13 08:46:26 -06:00
  • 5bd6cb52fb
    fix: github action canceling valid tasks for checking semantic pr title (#3127) Krzysztof Malczuk 2025-08-13 15:14:03 +01:00
  • fffdab4f5c
    fix: Dell distribution missing kvstore (#3113) Chacksu 2025-08-13 09:18:25 -04:00
  • 6358d0a478
    docs: reorganize contributor guide (#3110) Kelly Brown 2025-08-12 19:17:03 -04:00
  • 3d90117891
    chore(tests): fix responses and vector_io tests (#3119) Ashwin Bharambe 2025-08-12 16:15:53 -07:00
  • 1721aafc1f
    feat(responses): type file results properly (#3117) Ashwin Bharambe 2025-08-12 10:39:09 -07:00
  • 4fec49dfdb
    feat(responses): add include parameter (#3115) Ashwin Bharambe 2025-08-12 10:24:01 -07:00
  • 6812aa1e1e
    chore: bump min python version in docs and tests (#3103) Nathan Weinberg 2025-08-12 11:52:57 -04:00
  • 88c4fdc5d7
    chore(python-deps): bump chromadb from 1.0.15 to 1.0.16 (#3083) dependabot[bot] 2025-08-12 08:44:39 -07:00
  • 393f3714b0
    chore(python-deps): bump torch from 2.7.1 to 2.8.0 (#3082) dependabot[bot] 2025-08-12 08:44:24 -07:00
  • b70e2f1f09
    fix(dep): update to openai >= 1.99.6 and use new Function location (#3087) Matthew Farrellee 2025-08-12 10:40:32 -05:00
  • 4a13ef45e9
    fix: Implement missing run_moderation method in PromptGuardSafetyImpl (#3101) Mustafa Elbehery 2025-08-12 17:32:52 +02:00
  • 19123ca957
    refactor: standardize InferenceRouter model handling (#2965) Nathan Weinberg 2025-08-12 06:20:39 -04:00
  • 803114180b
    chore(logging)!: use comma as a delimiter (#3095) Ashwin Bharambe 2025-08-11 11:51:43 -07:00
  • f7adf58b1b
    docs: Add documentation on how to contribute a Vector DB provider and update testing documentation (#3093) Francisco Arceo 2025-08-11 12:11:09 -06:00
  • b5b5f5b9ae
    chore: add mypy prompt guard (#2678) Mustafa Elbehery 2025-08-11 17:40:40 +02:00
  • 7448a4a88c
    chore: Updating UI Sidebar (#3081) Francisco Arceo 2025-08-11 08:39:52 -06:00
  • 8faff92591
    chore: remove redundant code in unregister_toolgroup (#3092) Matthew Farrellee 2025-08-11 09:38:54 -05:00
  • a4bad6c0b4
    feat: Add Google Vertex AI inference provider support (#2841) Eran Cohen 2025-08-11 15:22:04 +03:00
  • 78a59a4dbe
    chore: Adding GitHub Stars, trends, and contributor shout out to README (#3079) Francisco Arceo 2025-08-10 19:11:14 -06:00
  • 69dc789e15
    docs: Add unsupported search mode info about FAISS (#3089) Varsha 2025-08-10 16:34:34 -07:00
  • ce72a28525
    docs: Update doc on search modes for Milvus (#3078) Varsha 2025-08-10 15:48:36 -07:00
  • 1677d6bffd
    feat: Flash-Lite 2.0 and 2.5 models added to Gemini inference provider (#3058) Vlastimil Eliáš 2025-08-08 22:48:15 +02:00
  • 0b5a794c27
    fix: telemetry logger spams when queue is full (#3070) ehhuang 2025-08-08 13:47:36 -07:00
  • 9b70bb9d4b
    feat(ui): Adding Vector Store Files to Admin UI (#3041) Francisco Arceo 2025-08-08 08:44:06 -06:00
  • 9e78f2da96
    docs: fix the docs for NVIDIA Inference Provider (#3055) Jiayi Ni 2025-08-08 02:27:55 -07:00
  • e90fe25890
    fix(tests): move llama stack client init back to fixture (#3071) Ashwin Bharambe 2025-08-07 15:29:53 -07:00
  • 5f1ddd35e4
    chore(tests): refactor and move responses tests away from verifications (#3068) Ashwin Bharambe 2025-08-07 13:48:16 -07:00
  • 342550c1e2
    docs: Added comment about a known limitation of AgentEventLogger (#2930) Dean Wampler 2025-08-07 13:09:57 -04:00
  • e3928e6a29
    feat: Implement hybrid search in Milvus (#2644) Varsha 2025-08-07 00:42:03 -07:00
  • 5a2d323eca
    docs: add use of custom exceptions to code style guide (#3049) Nathan Weinberg 2025-08-06 17:12:08 -04:00
  • 26d3d25c87
    feat: Add moderations create api (#3020) slekkala1 2025-08-06 13:51:23 -07:00
  • 0caef40e0d
    fix: telemetry fixes (inference and core telemetry) (#2733) Charlie Doern 2025-08-06 16:37:40 -04:00
  • c252dfa3ef
    fix(ci): allow tests to skip llama stack client instantiation (#3052) Ashwin Bharambe 2025-08-06 11:15:41 -07:00
  • 8ba04205ac
    docs: remove pure venv references (#3047) IAN MILLER 2025-08-06 18:42:34 +01:00
  • e9fced773a
    refactor: introduce common 'ResourceNotFoundError' exception (#3032) Nathan Weinberg 2025-08-06 13:22:55 -04:00
  • dfce05d0c5
    fix(docs): update llama stack build CLI doc (#3050) Ashwin Bharambe 2025-08-06 09:32:09 -07:00
  • 3e695cf320
    chore: update postgres_demo with new config (#3045) ehhuang 2025-08-06 07:48:40 -07:00
  • 7eff1bb3ec
    ci(pre-commit): enforce presence of 'upload-time' field in uv.lock (#2920) Mohamed Rebai 2025-08-06 15:46:59 +01:00
  • 7f834339ba
    chore(misc): make tests and starter faster (#3042) Ashwin Bharambe 2025-08-05 14:55:05 -07:00
  • e12524af85
    feat: create unregister shield API endpoint in Llama Stack (#2853) IAN MILLER 2025-08-05 15:33:46 +01:00
  • e565b91182 build: Bump version to 0.2.17 github-actions[bot] 2025-08-05 01:43:30 +00:00
  • ea46f74092 fix: rectify typo in MANIFEST.in due to #2975 Ashwin Bharambe 2025-08-04 18:22:49 -07:00
  • bb6b6041d6
    chore: fix: integration tests failures marked as successful (#3039) ehhuang 2025-08-04 17:06:28 -07:00
  • eac1e0c7d4
    chore: Fixing Markdown renderer (#3038) Francisco Arceo 2025-08-04 17:16:09 -04:00
  • 68b0071861
    chore: standardize session not found error (#3031) Nathan Weinberg 2025-08-04 16:12:02 -04:00
  • 05cfa213b6
    chore: standardize tool group not found error (#2986) Nathan Weinberg 2025-08-04 14:41:33 -04:00
  • 55a2694c80
    chore(python-deps): bump openai from 1.97.1 to 1.98.0 (#3025) dependabot[bot] 2025-08-04 11:40:56 -07:00
  • cc87995e2b
    chore: rename templates to distributions (#3035) Ashwin Bharambe 2025-08-04 11:34:17 -07:00
  • 12f964437a
    chore(python-deps): bump opentelemetry-exporter-otlp-proto-http from 1.35.0 to 1.36.0 (#3027) dependabot[bot] 2025-08-04 09:37:58 -07:00
  • 48b49e318f
    chore(python-deps): bump weaviate-client from 4.16.4 to 4.16.5 (#3026) dependabot[bot] 2025-08-04 09:37:31 -07:00
  • 4411e6e362
    chore(ci): remove reportlab dep (#3033) Matthew Farrellee 2025-08-04 11:36:13 -05:00
  • e5b542dd8e
    feat: switch to async completion in LiteLLM OpenAI mixin (#3029) Eran Cohen 2025-08-03 22:08:56 +03:00
  • dbfc15123e
    test: Implement vector store search test (#3001) Varsha 2025-08-02 15:57:38 -07:00
  • 3c2aee610d
    refactor: Remove double filtering based on score threshold (#3019) Varsha 2025-08-02 15:57:03 -07:00
  • 1e3b5aa9b8
    chore: CI action names (#3014) ehhuang 2025-08-02 15:56:42 -07:00
  • edc19698fb
    chore(python-deps): bump huggingface-hub from 0.34.2 to 0.34.3 (#3028) dependabot[bot] 2025-08-02 15:53:46 -07:00
  • a749d5f4a4
    refactor: remove Conda support from Llama Stack (#2969) IAN MILLER 2025-08-02 23:52:59 +01:00
  • f2eee4e417
    chore: create integration-tests script (#3016) ehhuang 2025-08-01 17:38:49 -07:00
  • 6ac710f3b0
    fix(recording): endpoint resolution (#3013) ehhuang 2025-08-01 16:23:54 -07:00
  • 140ee7d337
    fix: sambanova inference provider (#2996) Matthew Farrellee 2025-08-01 12:09:14 -04:00
  • 0527c0fb15
    chore: Update README for supported DBs (#3005) Francisco Arceo 2025-08-01 11:23:36 -04:00
  • 1f0766308d
    feat: Add openAI compatible APIs to Qdrant (#2465) Varsha 2025-07-31 21:41:34 -07:00
  • 194abe7734
    test: use llama stack build when starting server (#2999) ehhuang 2025-07-31 21:09:14 -07:00
  • 0b08d64ddb
    feat(ci): introduce workflow for re-recording inference outputs (#3002) Ashwin Bharambe 2025-07-31 17:30:47 -07:00
  • 33cca26154
    chore: Enabling Integration tests for Weaviate (#2882) Francisco Arceo 2025-07-31 20:29:50 -04:00
  • 369286f95b fix(ci): syntax error in the disabled workflow Ashwin Bharambe 2025-07-31 15:35:42 -07:00
  • 89ff93182c
    feat(ci): only run on 3.12, run on both 3.12 and 3.13 nightly (#3000) Ashwin Bharambe 2025-07-31 15:32:05 -07:00
  • f4489eeb83
    fix(ci): simplify integration tests replay mode (#2997) Ashwin Bharambe 2025-07-31 15:18:18 -07:00
  • 218c89fff1
    feat: Add clear error message when API key is missing (#2992) Matthew Farrellee 2025-07-31 16:33:16 -04:00
  • 22f79bdb9e fix(ci): lets attempt another fix for concurrency Ashwin Bharambe 2025-07-31 13:22:24 -07:00
  • 18576349ca fix(ci): simplified concurrency and job eligibility criteria Ashwin Bharambe 2025-07-31 13:11:04 -07:00
  • d1b300ead9 fix(ci, nvidia): do not use module level pytest skip for now Ashwin Bharambe 2025-07-31 12:31:40 -07:00
  • 752fd3b1c1 fix(ci): use single quotes please Ashwin Bharambe 2025-07-31 11:56:25 -07:00
  • 5ba25efd54 fix(ci): ensure workflow runs when manually run or scheduled Ashwin Bharambe 2025-07-31 11:54:51 -07:00
  • 27d866795c
    feat(ci): add support for running vision inference tests (#2972) Ashwin Bharambe 2025-07-31 11:50:42 -07:00
  • 709c974bd8
    fix: integration tests not triggering on PR open (#2985) Charlie Doern 2025-07-31 14:36:44 -04:00
  • b41d696e4f
    fix: Post Training Model change in Tests in order to make it less intensive (#2991) Nehanth Narendrula 2025-07-31 14:22:34 -04:00
  • ffb6306fbd
    fix: remove redundant code from unregister_vector_db (#2983) Nathan Weinberg 2025-07-31 12:22:04 -04:00
  • ea8dd58144
    chore: Remove coverage badge from README.md (#2976) Christian Zaccaria 2025-07-31 17:21:30 +01:00
  • 8a6c0fb930
    docs: Reformat external provider documentation (#2982) Kelly Brown 2025-07-31 12:21:13 -04:00
  • 3a574ef23c
    fix: remove unused DPO parameters from schema and tests (#2988) Nehanth Narendrula 2025-07-31 12:11:08 -04:00
  • 5c33bc1353
    fix: post_training ci (#2984) Charlie Doern 2025-07-31 11:26:06 -04:00
  • cf73146132
    feat: Enable DPO training with HuggingFace inline provider (#2825) Nehanth Narendrula 2025-07-31 02:33:36 -04:00
  • 2665f00102
    chore(rename): move llama_stack.distribution to llama_stack.core (#2975) Ashwin Bharambe 2025-07-30 23:30:53 -07:00
  • f3d5459647
    feat(UI): adding MVP playground UI (#2828) Francisco Arceo 2025-07-30 22:44:16 -04:00
  • d6ae2b0f47
    fix(ci): more correct concurrency key for workflows (#2973) Ashwin Bharambe 2025-07-30 18:23:14 -07:00
  • 406ca72957
    fix: remove redundant code from unregister_dataset (#2971) Nathan Weinberg 2025-07-30 19:40:01 -04:00
  • cb7354a9ce
    docs: Add detailed docstrings to API models and update OpenAPI spec (#2889) Sai Prashanth S 2025-07-30 16:32:59 -07:00
  • cd5c6a2fcd
    chore: standardize vector store not found error (#2968) Nathan Weinberg 2025-07-30 18:19:16 -04:00
  • 272a3e9937
    chore: standardize dataset not found error (#2962) Nathan Weinberg 2025-07-30 17:52:46 -04:00
  • 25d3dfa30f
    fix: fix No module named 'ollama' in test_inference_recordings.py (#2967) IAN MILLER 2025-07-30 21:33:33 +01:00
  • c5622c79de
    chore: standardize model not found error (#2964) Nathan Weinberg 2025-07-30 15:19:53 -04:00
  • 266e2afb9c
    fix(ci): slightly update workflow trigger (#2966) Ashwin Bharambe 2025-07-30 12:04:13 -07:00
  • 026caa5551
    docs: part 1 - fix warnings in documentation generation (#2861) Kelly Brown 2025-07-30 13:50:10 -04:00
  • 38d5c44354
    chore: fix k8s config (#2959) ehhuang 2025-07-30 10:11:59 -07:00
  • fd2aaf4978
    fix: use OLLAMA_URL to activate Ollama provider in starter (#2963) Ashwin Bharambe 2025-07-30 10:11:17 -07:00
  • b69bafba30
    fix(library_client): improve initialization error handling and prevent AttributeError (#2944) Matthew Farrellee 2025-07-30 11:58:47 -04:00
  • 9b69b6ac05 fix: pre-commit issue Ashwin Bharambe 2025-07-29 17:52:36 -07:00